© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 75053
    Prev
    Next
    INDEX
    Explanations

    various forms of academic authorship or references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AXB
    -0.08
    ureau
    -0.07
     Craw
    -0.07
    çuk
    -0.07
     пÑĢиклад
    -0.07
    &oacute
    -0.07
    सल
    -0.07
    istrar
    -0.06
    Į
    -0.06
     Jab
    -0.06
    POSITIVE LOGITS
    830
    0.06
    azo
    0.06
    APT
    0.06
    istani
    0.06
    oya
    0.06
    quared
    0.05
    ergy
    0.05
    elli
    0.05
    nown
    0.05
    _timeout
    0.05
    Activations Density 0.000%

    No Known Activations